From the source
OpenAI studies worst-case frontier risks of releasing gpt-oss by introducing malicious fine-tuning to elicit maximum capabilities in biology and cybersecurity.
From the source
In this paper, we study the worst-case frontier risks of releasing gpt-oss. We introduce malicious fine-tuning (MFT), where we attempt to elicit maximum capabilities by fine-tuning gpt-oss to be as capable as possible in two domains: biology and cybersecurity.
openai.com
